Composable Deep Reinforcement Learning for Robotic Manipulation.
Tuomas HaarnojaVitchyr PongAurick ZhouMurtaza DalalPieter AbbeelSergey LevinePublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- manipulation tasks
- real robot
- perception action
- function approximation
- robotic control
- mobile robot
- object manipulation
- imitation learning
- robotic arm
- robotic systems
- multi agent
- dynamic programming
- optimal policy
- robot control
- machine learning
- tactile sensing
- robot navigation
- real time
- learning algorithm
- motion planning
- temporal difference
- robotic tasks
- state space
- function approximators
- markov decision processes
- deep learning
- active learning
- reinforcement learning methods
- degrees of freedom
- multi agent reinforcement learning
- policy search
- markov decision process
- computer vision
- model free
- human operators